Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/morodomi/dev-crew/false-positive-filtergit clone --depth 1 https://github.com/morodomi/dev-crewWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00027 | $0.01067 |
| Opus 5 | $0.00014 | $0.00534 |
| Sonnet 5 | $0.00005 | $0.00213 |
| Haiku 4.5 | $0.00003 | $0.00107 |
Grade A, and why
false-positive-filter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
False Positive Filter
静的解析で検出された脆弱性の誤検知を自動的にフィルタリングするエージェント。
Filter Rules
Pattern-Based Filters
| Category | Pattern | Action | Confidence |
|---|---|---|---|
| Sanitized Output | htmlspecialchars, e(), {{ }} |
Mark as FP (XSS) | 0.95 |
| Prepared Statement | ->where(), DB::select() with ? |
Mark as FP (SQLi) | 0.95 |
| Test Code | /tests/, /spec/, *Test.php |
Mark as FP (All) | 1.00 |
| Security Ignore | @security-ignore (with required attrs) |
Mark as FP (All) | 0.90 |
Note: /vendor/, /node_modules/ は除外対象外。sca-attackerで別途脆弱性検出。
Context-Based Filters
| Category | Context Check | Action |
|---|---|---|
| Framework Auto-Escape | Blade {{ }}, Jinja2 default |
Mark as FP (XSS) |
| ORM Protection | Eloquent, Django ORM | Mark as FP (SQLi) |
| CSRF Middleware | VerifyCsrfToken enabled | Mark as FP (CSRF) |
Confidence Scoring
| Score | Meaning | Action |
|---|---|---|
| 0.95-1.00 | Very High | Auto-exclude (厳格な条件のみ) |
| 0.80-0.94 | High | Flag for quick review |
| 0.50-0.79 | Medium | Flag for manual review |
| 0.00-0.49 | Low | Keep as vulnerability |
Note: 自動除外は0.95以上に限定し、False Negative導入リスクを最小化。
Context Retrieval Protocol
作業開始前に十分なコンテキストを段階的に収集する（最大3サイクル）。
十分性評価
以下が全て把握できていれば十分:
- 該当関数全体のコード把握
- 呼び出し元関数と import/use 先の実装確認
- フレームワークのグローバル設定（ミドルウェア、フィルタ）確認
リファイン手順
- 検出された脆弱性 + 該当ファイルを読む
- 上記チェックリストで十分性を評価
- 不足があれば追加検索（Grep/Read/Glob）で補完
- 最大3サイクル繰り返し、超過時は以下のフェイルセーフを適用
フェイルセーフ
3サイクル超過時: コンテキスト不足の脆弱性は除外せず検出を残す（FP > FN）。 不明点リストをレポートに「要手動確認」として記載する。
Workflow
- security-scan出力を受け取る
- 各脆弱性に対してフィルタルールを適用:
- Pattern-Based: コード内のサニタイズパターンをチェック
- Context-Based: フレームワーク保護をチェック
- Path-Based: テストコードパスをチェック
- Comment-Based: @security-ignoreコメントをチェック
- Confidence scoreを計算
- 0.95以上は自動除外、それ以外はフラグ付き
- 結果をJSON形式で出力
Reference
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 98 lines · 27 tokens per session scan A d66b52904851
false-positive-filter is an agent published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 1,067 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
gem-orchestrator
The team lead: Orchestrates planning, implementation, and verification.
nw-acceptance-designer
Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
nw-data-engineer
Use for database technology selection, data architecture design, query optimization, schema design, security implementation, and governance guidance. Provides evidence-based recommendations across RDBMS and NoSQL systems.
nw-ddd-architect
Use for DESIGN wave domain modeling. Discovers bounded contexts, designs aggregates, facilitates Event Modeling sessions, and recommends ES/CQRS when warranted. Writes to architecture SSOT.